public inbox for linux-mm@kvack.org
 help / color / mirror / Atom feed
From: "David Hildenbrand (Arm)" <david@kernel.org>
To: Pedro Falcato <pfalcato@suse.de>,
	"Lorenzo Stoakes (Oracle)" <ljs@kernel.org>
Cc: Andrew Morton <akpm@linux-foundation.org>,
	"Liam R. Howlett" <Liam.Howlett@oracle.com>,
	Vlastimil Babka <vbabka@kernel.org>, Jann Horn <jannh@google.com>,
	Dev Jain <dev.jain@arm.com>, Luke Yang <luyang@redhat.com>,
	jhladky@redhat.com, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/4] mm/mprotect: un-inline folio_pte_batch_flags()
Date: Fri, 20 Mar 2026 12:02:17 +0100	[thread overview]
Message-ID: <076b36f7-1ed3-49ce-a892-eefd189870df@kernel.org> (raw)
In-Reply-To: <tv6pcikk456ynfx7lz3lrql3yafg4njuy3bzi4v6yi5hpe27gi@hakvdy2jmewu>


> 
> which the compiler FWIW tries to inline it all into one function, but then
> does a poor job at figuring things out. And the CPU gets confused too. It
> was frankly shocking how much performance I could squeeze out of a
> 
> if (nr_ptes == 1) {
> 	/* don't bother with the loops and the funny logic */
> }

Yes, same experience with fork/munmap.

-- 
Cheers,

David


  reply	other threads:[~2026-03-20 11:02 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-19 18:31 [PATCH 0/4] mm/mprotect: micro-optimization work Pedro Falcato
2026-03-19 18:31 ` [PATCH 1/4] mm/mprotect: encourage inlining with __always_inline Pedro Falcato
2026-03-19 18:59   ` Lorenzo Stoakes (Oracle)
2026-03-19 19:00     ` Lorenzo Stoakes (Oracle)
2026-03-19 21:28   ` David Hildenbrand (Arm)
2026-03-20  9:59     ` Pedro Falcato
2026-03-20 10:08       ` David Hildenbrand (Arm)
2026-03-19 18:31 ` [PATCH 2/4] mm/mprotect: move softleaf code out of the main function Pedro Falcato
2026-03-19 19:06   ` Lorenzo Stoakes (Oracle)
2026-03-19 21:33   ` David Hildenbrand (Arm)
2026-03-20 10:04     ` Pedro Falcato
2026-03-20 10:07       ` David Hildenbrand (Arm)
2026-03-20 10:54         ` Lorenzo Stoakes (Oracle)
2026-03-19 18:31 ` [PATCH 3/4] mm/mprotect: un-inline folio_pte_batch_flags() Pedro Falcato
2026-03-19 19:14   ` Lorenzo Stoakes (Oracle)
2026-03-19 21:41     ` David Hildenbrand (Arm)
2026-03-20 10:36       ` Lorenzo Stoakes (Oracle)
2026-03-20 10:59         ` Pedro Falcato
2026-03-20 11:02           ` David Hildenbrand (Arm) [this message]
2026-03-20 11:27           ` Lorenzo Stoakes (Oracle)
2026-03-20 11:01         ` David Hildenbrand (Arm)
2026-03-20 11:45           ` Lorenzo Stoakes (Oracle)
2026-03-23 12:56             ` David Hildenbrand (Arm)
2026-03-20 10:34     ` Pedro Falcato
2026-03-20 10:51       ` Lorenzo Stoakes (Oracle)
2026-03-19 18:31 ` [PATCH 4/4] mm/mprotect: special-case small folios when applying write permissions Pedro Falcato
2026-03-19 19:17   ` Lorenzo Stoakes (Oracle)
2026-03-20 10:36     ` Pedro Falcato
2026-03-20 10:42       ` Lorenzo Stoakes (Oracle)
2026-03-19 21:43   ` David Hildenbrand (Arm)
2026-03-20 10:37     ` Pedro Falcato
2026-03-20  2:42 ` [PATCH 0/4] mm/mprotect: micro-optimization work Andrew Morton

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=076b36f7-1ed3-49ce-a892-eefd189870df@kernel.org \
    --to=david@kernel.org \
    --cc=Liam.Howlett@oracle.com \
    --cc=akpm@linux-foundation.org \
    --cc=dev.jain@arm.com \
    --cc=jannh@google.com \
    --cc=jhladky@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=ljs@kernel.org \
    --cc=luyang@redhat.com \
    --cc=pfalcato@suse.de \
    --cc=vbabka@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox